Book a Call

Open Source

Tools and reference implementations for building production AI systems. Everything here is built for real-world use—not demos.

Eval-Gated RAG Platform

Reference implementation

Python

Production RAG with evaluation-driven CI/CD. Gold-set evals, 85% SLO gate, and mock-based harness for CI. Qdrant, embeddings, Ollama/vLLM. See case study for architecture and results.

EvaluationCI/CDGold Sets
View on GitHubCase study

Private Doc-Intelligence Platform

Reference implementation

HelmPython

Document intelligence for regulated environments. OCR (Tesseract/PaddleOCR), extraction (OpenAI/Ollama/local), gold-set eval, Helm and Kustomize. Deploy locally with docker-compose or on K8s. See case study for metrics and architecture.

KubernetesOCRDocument AIReference Architecture
View on GitHubCase study

Philosophy

Most open-source AI projects are demos, they show what's possible but skip the hard parts of production. These projects are different. They're built to solve real problems:

  • Eval-first — Every project includes evaluation tooling. If you can't measure it, you can't trust it.
  • Production-ready — Helm charts, dashboards, rollback plans. Not just a Python script.
  • Well-documented — READMEs that explain the tradeoffs, not just the happy path.
  • Private-first — Everything runs in your environment. No external APIs, no data leaks.

More Projects in Progress

Currently building reusable components and reference implementations. These will be open-sourced once properly documented and tested.

Follow me on GitHub for updates, or get in touch if you have specific needs.

Need help deploying private AI systems in your environment?

Book a CallView Services